Intelligent identification method and system for traditional Chinese medicine constitution information of type II diabetes mellitus

Abstract

The embodiment of the invention discloses a method for acquiring face spectral information of a type II diabetes patient; the face spectrum information is input into a pre-constructed model, corresponding traditional Chinese medicine constitution information is output, the traditional Chinese medicine constitution information comprises mild constitution, yin deficiency constitution, yang deficiency constitution, phlegm-dampness constitution, blood stasis constitution, qi deficiency constitution, qi depression constitution, specific intrinsic constitution and damp-heat constitution, and the pre-trained model is a model constructed based on a partial least square method. The purpose of non-contact judgment of the traditional Chinese medicine constitution information of the type II diabetes mellitus is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of information processing, and particularly to an intelligent recognition method and system for the traditional Chinese medicine constitution information of type II diabetes mellitus. Background Art

[0002] Type II diabetes mellitus is also known as non-insulin-dependent diabetes mellitus. Constitution identification helps to discover the constitution types prone to diabetes, which has extremely important clinical value for the prevention and treatment of diabetes in traditional Chinese medicine.

[0003] Therefore, there is an urgent need to implement a reliable non-contact identification of the traditional Chinese medicine constitution for type II diabetes mellitus. Summary of the Invention

[0004] The main object of the present invention is to provide an intelligent recognition method and system for the traditional Chinese medicine constitution information of type II diabetes mellitus to solve the deficiencies in the related technologies.

[0005] To achieve the above object, according to the first aspect of the present invention, an intelligent recognition method for the traditional Chinese medicine constitution information of type II diabetes mellitus is provided, including obtaining the face spectral information of type II diabetes mellitus patients; inputting the face spectral information into a pre-constructed model to output the corresponding traditional Chinese medicine constitution information, where the traditional Chinese medicine constitution information includes peaceful constitution, yin deficiency constitution, yang deficiency constitution, phlegm-dampness constitution, blood stasis constitution, qi deficiency constitution, qi stagnation constitution, special endowment constitution, and damp-heat constitution, and the pre-trained model is a model constructed based on the partial least squares method.

[0006] Optionally, when constructing the model, the method includes: collecting information in multiple dimensions from the face sample set of type II diabetes mellitus patients to obtain feature data, where the feature data includes the face spectral information and human feature information of different type II diabetes mellitus samples; based on the feature data, constructing a variable matrix X corresponding to the feature data; constructing a variable matrix Y based on each sample in the face sample set of type II diabetes mellitus patients; using the partial least squares method to model the variable matrix X and the variable matrix Y, and in the execution of the partial least squares method, gradually constructing a projection vector to form a regression model.

[0007] Optionally, using a near-infrared acquisition system to collect the face spectral information of type II diabetes mellitus patients, where the near-infrared acquisition system includes: a near-infrared imaging device emitting near-infrared light; receiving the photoelectric pulse wave corresponding to the outgoing light of each wavelength through a spectroscope; performing signal conversion on the photoelectric pulse wave based on a photoelectric converter and an analog-to-digital converter to obtain the changing outgoing light intensity data; calculating the absorbance data of different components based on the changing outgoing light intensity data, where the absorbance data includes the absorbance data of blood glucose concentration; determining the spectra of different components based on the absorbance data and processing the spectra to obtain a blood component spectrogram.

[0008] Optionally, processing the spectral sample to obtain a blood component spectrogram includes: using the Euclidean distance to determine the discrete points of the spectral sample, and removing invalid spectral samples to obtain valid spectral samples; using the wavelet transform denoising method to remove the interference noise of the spectral sample; removing the spectral baseline of the spectral sample; performing normalization processing to obtain a blood component spectrogram.

[0009] According to a second aspect of the present invention, there is provided an intelligent recognition system for type II diabetes traditional Chinese medicine constitution information, including a near-infrared acquisition subsystem for acquiring the face spectral information of type II diabetic patients;

[0010] An intelligent recognition subsystem that processes the face spectral information using a pre-trained model to identify the corresponding traditional Chinese medicine constitution information, where the traditional Chinese medicine constitution information includes peaceful constitution, yin deficiency constitution, yang deficiency constitution, phlegm-dampness constitution, blood stasis constitution, qi deficiency constitution, qi stagnation constitution, special endowment constitution, and damp-heat constitution, and the pre-trained model is a model constructed based on partial least squares method.

[0011] Optionally, collect information from multiple dimensions in the type II diabetic face sample set to obtain feature data, where the feature data includes face spectral information and human feature information of different type II diabetic samples; based on the feature data, construct a variable matrix X corresponding to the feature data; construct a variable matrix Y based on each sample in the type II diabetic face sample set; use the partial least squares method to model the variable matrix X and the variable matrix Y, and in the process of performing the partial least squares method, gradually construct a projection vector to form a regression model.

[0012] Optionally, the near-infrared acquisition system includes: a near-infrared imaging device that emits near-infrared light; receiving the photoelectric pulse wave corresponding to the outgoing light of each wavelength through a spectroscope; performing signal conversion on the photoelectric pulse wave based on a photoelectric converter and an analog-to-digital converter to obtain changing outgoing light intensity data; calculating absorbance data of different components according to the changing outgoing light intensity data, where the absorbance data includes absorbance data of blood glucose concentration; determining the spectra of different components based on the absorbance data, and processing the spectra to obtain a blood component spectrogram.

[0013] Optionally, processing the spectral sample to obtain a blood component spectrogram includes: using the Euclidean distance to determine the discrete points of the spectral sample, and removing invalid spectral samples to obtain valid spectral samples; using the wavelet transform denoising method to remove the interference noise of the spectral sample; removing the spectral baseline of the spectral sample; performing normalization processing to obtain a blood component spectrogram.

[0014] According to a third aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing the computer to execute the method according to any one of the first aspects.

[0015] According to a fourth aspect of the present invention, there is provided an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to cause the at least one processor to execute the method according to any one of the implementation manners of the first aspect.

[0016] The intelligent recognition method and system for traditional Chinese medicine constitution information of type II diabetes in this embodiment. The method includes obtaining the face spectrum information of type II diabetes patients; inputting the face spectrum information into a pre-constructed model to output the corresponding traditional Chinese medicine constitution information, wherein the traditional Chinese medicine constitution information includes peaceful constitution, yin deficiency constitution, yang deficiency constitution, phlegm-dampness constitution, blood stasis constitution, qi deficiency constitution, qi stagnation constitution, special endowment constitution, and damp-heat constitution, and the pre-trained model is a model constructed based on partial least squares method. The purpose of non-contact judgment of traditional Chinese medicine constitution information of type II diabetes is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of the intelligent recognition method for traditional Chinese medicine constitution information of type II diabetes in an embodiment of the present invention;

[0019] Figure 2 It is a schematic diagram of the electronic device in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] In order to enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0021] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so as to implement the embodiments of the present invention described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0022] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in combination with the embodiments.

[0023] According to an embodiment of the present invention, there is provided an intelligent recognition method for the traditional Chinese medicine constitution information of type II diabetes, as Figure 1 shown, including the following steps 101 to step 103:

[0024] Step 101: Obtain the face spectral information of type II diabetic patients.

[0025] Step 102: Input the face spectral information into a pre-trained model, and output the corresponding traditional Chinese medicine constitution information, where the traditional Chinese medicine constitution information includes balanced constitution, yin deficiency constitution, yang deficiency constitution, phlegm-dampness constitution, blood stasis constitution, qi deficiency constitution, qi stagnation constitution, special endowment constitution, and damp-heat constitution, and the pre-trained model is a model constructed based on partial least squares method.

[0026] In this embodiment, the near-infrared video technology is adopted. By collecting the dynamic spectrum of the face video, a PLS-DA discriminant model is constructed using the partial least squares method to construct a traditional Chinese medicine constitution identification model corresponding to the characteristic variable sample data of type 2 diabetic patients, and then the face spectral sample of the type 2 diabetic patient to be tested is input to obtain the result of the corresponding traditional Chinese medicine constitution identification, so as to solve the problem of non-contact and non-invasive detection of the traditional Chinese medicine constitution of type 2 diabetes.

[0027] Before constructing the model, samples can be constructed. A certain number of near-infrared spectral images of the face videos of type 2 diabetic patients are collected, and the spectral processing is performed on the near-infrared spectral images to obtain the blood glucose concentration (including fasting blood glucose and postprandial blood glucose) of type 2 diabetic patients and the sample data sets such as the age, gender, and body mass index of the above-mentioned type 2 diabetic patients; perform univariate analysis and multivariate Logistic regression analysis on the above data sets to screen out characteristic variables; use the partial least squares method to construct a traditional Chinese medicine PLS-DA identification model corresponding to the characteristic variable sample data of type 2 diabetic patients.

[0028] As an optional implementation manner of this embodiment, when constructing the model, the method includes: collecting information in multiple dimensions from the type II diabetic human face sample set to obtain feature data, where the feature data includes different type II diabetic human face spectral information and human body feature information; based on the feature data, constructing a variable matrix X corresponding to the feature data; constructing a variable matrix Y based on each sample in the type II diabetic human face sample set; using the partial least squares method to model the variable matrix X and the variable matrix Y, where in the execution of the partial least squares method, projection vectors are gradually constructed to form a regression model.

[0029] In this optional implementation manner, the partial least squares regression analysis method is a statistical method. It is related to the principal component regression, but instead of finding the hyperplane with the largest variance between the response variable and the independent variable, it projects the predictive variables and the observed variables onto a new space through projection to find a linear regression model. It includes: when there is potential multicollinearity and the number of observations is less than the number of variables, after selecting the latent variables according to the cross-validation results, setting a threshold. If the predicted value is greater than the threshold, it belongs to the current category; when the predicted value is less than the threshold, it does not belong to the current category.

[0030] Further, when constructing the PLS-DA discrimination model based on the partial least squares method and inputting the preprocessed data into the PLS-DA identification model for training to obtain the optimal PLS-DA identification model, it further includes: selecting the optimal number of latent variables to construct the PLS-DA identification model. Further, when constructing the PLS-DA identification model based on the partial least squares method and inputting the preprocessed data into the PLS-DA identification model for training to obtain the optimal PLS-DA identification model, it includes: dividing the preprocessed data into a training set, a validation set, and a test set; training the PLS-DA identification model based on the training set; evaluating the performance of the trained PLS-DA identification model based on the validation set to obtain a PLS-DA identification model that meets the performance conditions; evaluating the prediction results of the PLS-DA identification model that meets the performance conditions based on the test set to obtain the identification index corresponding to the PLS-DA identification model.

[0031] Further, when inputting the infrared spectrum diagram to be discriminated into the optimal PLS-DA identification model to obtain the identification result of the traditional Chinese medicine constitution category corresponding to the infrared spectrum diagram to be discriminated, where the identification result includes the balanced constitution and the biased constitutions (including the yin-deficiency constitution, yang-deficiency constitution, phlegm-dampness constitution, blood stasis constitution, qi-deficiency constitution, qi stagnation constitution, special endowment constitution, damp-heat constitution, etc.), it further includes:

[0032] When Ypre > 0.5, it is determined that the infrared spectrum diagram to be identified is of the balanced constitution;

[0033] When Ypre < 0.5, it is determined that the infrared spectrum diagram to be identified is of the biased constitution.

[0034] For the identification of specific types of biased constitutions, and so on.

[0035] As an alternative implementation of this embodiment, a near-infrared acquisition system is used to acquire the face spectral information of type II diabetic patients. Among them, the near-infrared acquisition system includes: a near-infrared imaging device that emits near-infrared light; a photoelectric pulse wave corresponding to the outgoing light of each wavelength is received through a spectroscope; signal conversion of the photoelectric pulse wave is performed based on a photoelectric converter and an analog-to-digital converter to obtain changing outgoing light intensity data; absorbance data of different components are calculated according to the changing outgoing light intensity data, where the absorbance data includes absorbance data of blood glucose concentration; based on the absorbance data, spectra of different components are determined, and the spectra are processed to obtain a blood component spectrogram.

[0036] In this alternative implementation, the same method is used for sample processing, and thus a blood component spectrogram of the sample can also be obtained. A spectral database is constructed according to the blood component spectrogram; the spectral database has a diagnostic standard database for type 2 diabetes according to the diagnostic criteria of blood glucose concentration and content (including fasting blood glucose and postprandial blood glucose) of type 2 diabetic patients, as well as sample data sets such as age, gender, and body mass index of the above type 2 diabetic patients; univariate analysis and multivariate Logistic regression analysis are performed on the above data sets to screen out characteristic variables.

[0037] In the process of using Logistic regression analysis to establish an identification model, the stepwise regression method is used. After each variable is introduced into the equation, statistical tests are performed on each independent variable already introduced into the equation to check whether some independent variables that have degenerated into having no statistical significance need to be removed. The above two-way screening process is repeated until there are no independent variables outside the equation that can be introduced and no independent variables inside the equation that can be removed, and a locally optimal regression equation is obtained.

[0038] That is, for the characteristic data of each modality, different methods are used for feature extraction respectively, and then these features (including text ones, such as male, female; data ones, such as 7.0 mmol / L, etc.) are fused to integrate the characteristic information of different modalities, establish a fused characteristic set, and then use the association rule algorithm to obtain the final cognitive probability and result. In this way, the information characteristics of a single modality are retained, and the characteristic information of multiple modalities can be comprehensively utilized, improving the reliability of the final cognitive decision.

[0039] For example, the diagnostic criteria for type 2 diabetes are mainly related to blood glucose. The following are the specific diagnostic criteria:

[0040] 1) Fasting blood glucose: Fasting blood glucose refers to the blood glucose level measured after at least 8 hours without food intake. If fasting blood glucose ≥ 7.0 mmol / L, it meets the diagnostic criteria for type 2 diabetes;

[0041] 2) Postprandial blood glucose: Postprandial blood glucose refers to the blood glucose level measured within 2 hours after eating. If postprandial blood glucose ≥ 11.1 mmol / L, it meets the diagnostic criteria for type 2 diabetes;

[0042] 3) Random blood glucose: Random blood glucose refers to the blood glucose level measured at any time of the day. If random blood glucose ≥ 11.1 mmol / L and is accompanied by typical diabetic symptoms (such as polyuria, polydipsia, polyphagia, and unexplained weight loss), it meets the diagnostic criteria for type 2 diabetes.

[0043] For example, the type 2 diabetes group is mainly composed of yin deficiency constitution, qi deficiency constitution, and phlegm-dampness constitution. The physical characteristics of the type 2 diabetes group are mainly yin deficiency, qi deficiency, and phlegm-dampness.

[0044] For example, taking gender as an example. The distribution of traditional Chinese medicine constitution types in type 2 diabetes patients of different genders is different. Among male patients, yin deficiency constitution is the main one, followed by phlegm-dampness constitution, qi deficiency constitution, and peaceful constitution. Among them, the number of patients with phlegm-dampness constitution is significantly more than that of female patients; among female patients, yin deficiency constitution and qi deficiency constitution are the main ones, followed by yang deficiency constitution, phlegm-dampness constitution, and peaceful constitution. Among them, the number of patients with qi deficiency constitution and yang deficiency constitution is significantly more than that of male patients.

[0045] For example, taking age as an example. The number of patients with qi deficiency constitution and yang deficiency constitution in type 2 diabetes patients increases with the increase of the patient's age.

[0046] For example, taking body weight as an example. The body mass index of the yin deficiency constitution, qi deficiency constitution, peaceful constitution, and yang deficiency constitution groups is significantly lower than that of the phlegm-dampness constitution group when compared; the body mass index of the yin deficiency constitution, yang deficiency constitution, and qi deficiency constitution groups is lower than that of the peaceful constitution group when compared; among the five main traditional Chinese medicine constitution types of yin deficiency constitution, qi deficiency constitution, phlegm-dampness constitution, yang deficiency constitution, and peaceful constitution, the body mass index of the phlegm-dampness constitution group is significantly higher than that of the other four constitution groups.

[0047] This embodiment explores the distribution characteristics of traditional Chinese medicine (TCM) constitutions in type 2 diabetes patients and their relationships with patient gender, age, and body mass index, opening up new clinical ideas for the prevention and treatment of type 2 diabetes. The embodiments of the present invention have the following advantages: The non-contact identification method and system for TCM constitutions in type 2 diabetes based on dynamic spectroscopy technology in the present invention use near-infrared dynamic spectroscopy technology to perform infrared spectral scanning on the human face, obtain all spectral information of blood samples under the human skin at infrared wavelengths, and use the partial least squares (PLS-DA) discriminant model to construct a TCM constitution identification model corresponding to the characteristic variable sample data of type 2 diabetes patients, realizing non-contact identification of TCM constitutions in type 2 diabetes. This invention has the advantages of simple and convenient operation, greatly shortening the detection time, and being non-invasive and non-destructive.

[0048] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0049] According to an embodiment of the present invention, there is also provided an intelligent identification system for TCM constitution information of type II diabetes, including a near-infrared acquisition subsystem for acquiring facial spectral information of type II diabetes patients; and an intelligent identification subsystem for processing the facial spectral information using a pre-trained model to identify the corresponding TCM constitution information, where the TCM constitution information includes peaceful constitution, yin deficiency constitution, yang deficiency constitution, phlegm-dampness constitution, blood stasis constitution, qi deficiency constitution, qi stagnation constitution, special endowment constitution, and damp-heat constitution, and the pre-trained model is a model constructed based on partial least squares method.

[0050] As an optional implementation manner of this embodiment, information in multiple dimensions is collected from the type II diabetes patient face sample set to obtain characteristic data, where the characteristic data includes facial spectral information of different type II diabetes patient samples and human characteristic information; based on the characteristic data, a variable matrix X corresponding to the characteristic data is constructed; a variable matrix Y is constructed based on each sample in the type II diabetes patient face sample set; and partial least squares method is used to model the variable matrix X and the variable matrix Y, where in the execution of the partial least squares method, projection vectors are gradually constructed to form a regression model.

[0051] As an optional implementation manner of this embodiment, the near-infrared acquisition system includes: a near-infrared imaging device that emits near-infrared light; receiving photoelectric pulse waves corresponding to the emitted light of each wavelength through a spectroscope; performing signal conversion on the photoelectric pulse waves based on a photoelectric converter and an analog-to-digital converter to obtain varying emitted light intensity data; calculating absorbance data of different components according to the varying emitted light intensity data, where the absorbance data includes absorbance data of blood glucose concentration; determining spectra of different components based on the absorbance data, and processing the spectra to obtain a blood component spectrogram.

[0052] As an optional implementation manner of this embodiment, processing the spectral sample to obtain a blood component spectrogram includes: using the Euclidean distance to judge discrete points of the spectral sample, and removing invalid spectral samples to obtain valid spectral samples; using the wavelet transform denoising method to remove interference noise of the spectral sample; removing the spectral baseline of the spectral sample; performing normalization processing to obtain a blood component spectrogram.

[0053] According to an embodiment of the present invention, the present invention also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to implement the method described in any of the above embodiments.

[0054] According to an embodiment of the present invention, the present invention also provides a readable storage medium, which stores computer instructions for enabling a computer to implement the method described in any of the above embodiments when executed.

[0055] Figure 2 A schematic block diagram of an exemplary electronic device 300 that can be used to implement the embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices.

[0056] As Figure 2As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to computer programs stored in a read-only memory (ROM) 302 or computer programs loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0057] Multiple components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a magnetic disk, an optical disc, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0058] The computing unit 301 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 301 executes the various methods and processes described above, such as the object matching method. For example, in some embodiments, the object matching method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the method described above can be executed.

[0059] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0060] The program code for implementing the methods of the present invention may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0061] In the context of the present invention, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Claims

1. An intelligent identification method for TCM constitution information of type 2 diabetes, characterized in that: include: Obtain facial spectrum information of type Ⅱ diabetes; The facial spectrum information is input into a pre-built model, and the corresponding TCM constitution information is output, wherein the TCM constitution information includes balanced constitution, yin deficiency constitution, yang deficiency constitution, phlegm-damp constitution, blood stasis constitution, qi deficiency constitution, qi stagnation constitution, special constitution, and damp-heat constitution, wherein the pre-trained model is a model constructed based on partial least squares method.

2. The intelligent identification method of TCM constitution information of type 2 diabetes according to claim 1, characterized in that: When building a model, methods include: Collect information of multiple dimensions from a set of type 2 diabetes face samples to obtain feature data, wherein the feature data includes face spectrum information and human body feature information of different type 2 diabetes samples; Based on the feature data, construct a variable matrix X corresponding to the feature data; Construct variable matrix Y based on each sample in the type Ⅱ diabetes face sample set; The variable matrix X and the variable matrix Y are modeled using the partial least squares method, wherein in the implementation of the partial least squares method, projection vectors are gradually constructed to form a regression model.

3. The intelligent identification method of TCM constitution information of type 2 diabetes according to claim 1, characterized in that: The near infrared acquisition system is used to collect the face spectrum information of type 2 diabetes, wherein the near infrared acquisition system comprises: The near-infrared camera device emits near-infrared light; the photoelectric pulse wave corresponding to the emitted light of each wavelength is received through the spectrometer; The photoelectric pulse wave is converted into a signal based on a photoelectric converter and an analog-to-digital converter to obtain the changing output light intensity data; Calculating absorbance data of different components according to the changed output light intensity data, wherein the absorbance data includes absorbance data of blood sugar concentration; The spectra of different components are determined based on the absorbance data, and the spectra are processed to obtain a blood component spectrum graph.

4. The intelligent identification method of TCM constitution information of type 2 diabetes according to claim 1, characterized in that: Processing the spectrum sample to obtain a blood cost spectrum graph includes: Using Euclidean distance to determine the discrete points of the spectrum sample, and eliminating invalid spectrum samples to obtain valid spectrum samples; The wavelet transform denoising method is used to remove the interference noise of the spectral sample; the spectral baseline of the spectral sample is removed; and normalization processing is performed to obtain a blood component spectrum.

5. An intelligent identification system for TCM constitution information of type 2 diabetes, characterized in that: It includes a near-infrared acquisition subsystem to collect facial spectrum information of type 2 diabetes patients; The intelligent recognition subsystem uses a pre-trained model to process the facial spectrum information and identify the corresponding TCM constitution information, wherein the TCM constitution information includes balanced constitution, yin deficiency constitution, yang deficiency constitution, phlegm-damp constitution, blood stasis constitution, qi deficiency constitution, qi stagnation constitution, special constitution, and damp-heat constitution, wherein the pre-trained model is a model constructed based on the partial least squares method.

6. The intelligent identification system of TCM constitution information of type II diabetes according to claim 5, characterized in that: Information of multiple dimensions is collected from a face sample set of type 2 diabetes to obtain feature data, wherein the feature data includes face spectrum information and human feature information of different type 2 diabetes samples; based on the feature data, a variable matrix X corresponding to the feature data is constructed; based on each sample in the face sample set of type 2 diabetes, a variable matrix Y is constructed; partial least squares method is used to model the variable matrix X and the variable matrix Y, wherein in executing the partial least squares method, projection vectors are gradually constructed to form a regression model.

7. The intelligent identification system of TCM constitution information of type 2 diabetes according to claim 6 is characterized in that: The near-infrared acquisition system includes: a near-infrared camera device emitting near-infrared light; receiving photoelectric pulse waves corresponding to the outgoing light of each wavelength through a spectrometer; performing signal conversion on the photoelectric pulse waves based on a photoelectric converter and an analog-to-digital converter to obtain variable outgoing light intensity data; calculating absorbance data of different components based on the variable outgoing light intensity data, wherein the absorbance data includes absorbance data of blood glucose concentration; determining spectra of different components based on the absorbance data, and processing the spectra to obtain a blood component spectrum diagram.

8. The intelligent identification system of TCM constitution information of type 2 diabetes according to claim 7 is characterized in that: Processing the spectral samples to obtain a blood cost spectrum diagram includes: using Euclidean distance to determine discrete points of the spectral samples, and eliminating invalid spectral samples to obtain valid spectral samples; using wavelet transform denoising to eliminate interference noise of spectral samples; removing the spectral baseline of spectral samples; performing normalization processing to obtain a blood component spectrum diagram.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 4.

10. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the method described in any one of claims 1 to 4.

Images